© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18704
    Prev
    Next
    INDEX
    Explanations

    words related to illegality or illegal actions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ็จ
    -0.81
    𝘇
    -0.75
    kast
    -0.73
    Kast
    -0.71
     Gump
    -0.71
    CELLANEOUS
    -0.71
     Waray
    -0.69
     envies
    -0.68
    ValueStyle
    -0.66
    Rost
    -0.66
    POSITIVE LOGITS
     illeg
    1.08
     Illegal
    1.00
    illegal
    0.97
     illegal
    0.96
    Illegal
    0.88
     ilegal
    0.88
     illegally
    0.86
     gills
    0.85
     ileg
    0.85
    LEGAL
    0.82
    Activations Density 0.006%

    No Known Activations